---
language: da
datasets:
  - common-voice-9
  - nst
tags:
- speech-to-text
license: apache-2.0
---

# xls-r-300m-danish-nst-cv9

This is a version of [chcaa/xls-r-300m-danish](https://huggingface.co/chcaa/xls-r-300m-danish) finetuned for Danish ASR on the training set of the public NST dataset and the Danish part of Common Voice 9. The model is trained on 16kHz, so ensure that you use the same sample rate. 

The model was trained using fairseq with [this config](https://github.com/centre-for-humanities-computing/Gjallarhorn/blob/main/fairseq_configs/finetuning/xlrs_finetune.yaml) for 120.000 steps. 


## Usage
```Python
import torch
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor

# load model and tokenizer
processor = Wav2Vec2Processor.from_pretrained(
    "chcaa/xls-r-300m-danish-nst-cv9")
model = Wav2Vec2ForCTC.from_pretrained(
    "chcaa/xls-r-300m-danish-nst-cv9")

# load dataset and read soundfiles
ds = load_dataset("Alvenir/alvenir_asr_da_eval", split="test")

# tokenize
input_values = processor(
    ds[0]["audio"]["array"], return_tensors="pt", padding="longest"
).input_values  # Batch size 1

# retrieve logits
logits = model(input_values).logits

# take argmax and decode
predicted_ids = torch.argmax(logits, dim=-1)
transcription = processor.batch_decode(predicted_ids)
print(transcription)
```

## Performance
The table below shows the WER rate (greedy, no language model) of four different Danish ASR models on three publicly available datasets (lower is better).

|Model                                  | [Alvenir](https://huggingface.co/datasets/Alvenir/alvenir_asr_da_eval)|   [NST](https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-19/)|     [CV9.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_9_0)|
|:--------------------------------------|------:|-----:|-----:|
|[Alvenir/wav2vec2-base-da-ft-nst](https://huggingface.co/Alvenir/wav2vec2-base-da-ft-nst)        |  0.202| 0.099| 0.238|
|[chcaa/alvenir-wav2vec2-base-da-nst-cv9](https://huggingface.co/chcaa/alvenir-wav2vec2-base-da-nst-cv9) |  0.233| 0.126| 0.256|
|[chcaa/xls-r-300m-nst-cv9-da](https://huggingface.co/chcaa/xls-r-300m-nst-cv9-da)            |  0.105| 0.060| 0.119|
|chcaa/xls-r-300m-danish-nst-cv9        |  0.082| 0.051| 0.108|

The model was finetuned in collaboration with [Alvenir](https://alvenir.ai).